Analysis of spatial partitioning approaches for image classification

Author

Avramovic, Aleksej ; Risojevic, Vladimir

Author_Institution

Sch. of Electr. Eng., Univ. of Belgrade, Belgrade, Serbia

fYear

2014

fDate

25-27 Nov. 2014

Firstpage

211

Lastpage

216

Abstract

Spatial partitioning is proven to be beneficial for the tasks of image classification, scene categorization and object recognition. The most popular method to capture rough spatial structure of the scene is spatial pyramid matching. However, spatial pyramid matching results in an image representation that is sensitive to rotations. In this research we investigate the influence of upright and rotated partitions on image classification regardless of the image filtering step. We show that simple combination of rotated spatial partitions improves classification accuracy up to 10% compared to single spatial partition commonly used in spatial pyramid matching.

Keywords

image classification; image matching; image representation; object recognition; image classification; image filtering step; image representation; object recognition; rough spatial structure; scene categorization; spatial partitioning approach; spatial pyramid matching; Accuracy; Feature extraction; Filtering; Histograms; Image classification; Layout; Training; Image classification; rotation invariance; spatial pyramid matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Network Applications in Electrical Engineering (NEUREL), 2014 12th Symposium on

Conference_Location

Belgrade

Print_ISBN

978-1-4799-5887-0

Type

conf

DOI

10.1109/NEUREL.2014.7011509

Filename

7011509